Considering the problems of high cost, inefficiency, and time consumption of manual diagnosis of strawberry diseases, G-ResNet50 is proposed based on transfer learning and deep residual network for strawberry disease identification and classification. The G-ResNet50 is based on the ResNet50, and the focal loss function is introduced in G-ResNet50 to make the model devote itself to disease images that are difficult to classify. During the training process of the G-ResNet50 model, its convolutional layer and pooling layer inherit the pre-trained weight parameters from the ResNet50 model on the PlantVillage dataset, while adding dropout regularization and batch regularization methods to optimize the network model. The strawberry disease dataset includes four sample images of healthy plants, powdery mildew, strawberry anthracnose, and leaf spot disease. The dataset is enhanced and expanded by operations including angle rotation, adjusting contrast and brightness, and adding Gaussian noise. Compared with existing models such as VGG16, ResNet50, InceptionV3, and MobileNetV2, the results of model training and testing on 7,525 four-category leaf datasets show that the G-ResNet50 model has faster convergence speed and better classification effect, and its average recognition accuracy rate reached 98.67%, which is significantly higher than other models. Through the three evaluation indicators of precision rate, recall rate, and confusion matrix, it is concluded that the G-ResNet50 has good robustness, high stability, and high recognition accuracy and can provide a feasible solution for strawberry disease detection in practical applications.

With the increasing deployment of network technologies in industrial control systems (ICSs), cybersecurity has become a challenge in ICSs. Cybersecurity risk assessment (CRA) plays an important role in cybersecurity protection of ICSs. However, the weights of risk indices are constants in traditional CRA methods, and they do not fully consider the requirements of risk identification. In this paper, we define a novel order- $\alpha $ divergence measure for interval-valued intuitionistic fuzzy numbers (IVIFNs) and further develop a novel CRA approach for ICSs based on the proposed divergence measure under an interval-valued intuitionistic fuzzy environment to contribute to the research gap. First, an order- $\alpha $ divergence measure for IVIFNs is defined considering flexibility and robustness of divergence measures with the parameter. Next, a variable weight-based CRA approach for ICSs is developed. In this approach, IVIFNs are adopted to describe evaluation values of risk indices. The weights of risk indices are variable weight vectors and they are determined by the relative divergence closeness. Integration approaches of each node and each attack path in attack-defense trees (ADTs) are proposed based on the operations of IVIFNs, and risk scores of each attack path are calculated by using the score function. Finally, we apply the proposed method to the CRA of a civil aviation fuel supply automatic control system and verify its effectiveness and advantages by comparing it with other methods. This method can dynamically adjust the weights of risk indices considering the relationship between each risk index and the highest risk, and therefore, it can more effectively recognize the highest risk of ICSs than the traditional CRA method. In addition, it can also match the risk attitude of decision-makers by adjusting the parameter $\alpha $ .

Thermal battery is an ideal power supply for military applications such as artillery and ship equipment. Due to the sheet-type process of the thermal battery, various installation error defects occur in the assembly of thermal battery. Aiming at the problems of low efficiency and low defect-recognition rate of thermal battery detection, a thermal battery defect detection model is proposed based on residual network. First, the squeeze-and-excitation networks (SENet) structure based on the attention mechanism is introduced into residual block of the residual neural network, the connection between the feature extraction channels is established, and the improved deep residual network I-ResNet50 is obtained; Second, in order to prevent overfitting, the defect images processed in the production line and the laboratory are data-enhanced and labeled. Transfer learning strategy is introduced into the recognition model I-ResNet50, and then the training set data samples are input into the recognition model I-ResNet50 for training, and the activation function LReLu and Dropout skills are introduced to improve the classification ability of the I-ResNet50 model; Finally, the recognition model I-ResNet50 is applied to the test set and validation set, and each defect of the thermal battery are output. Comparison experiments are tested under different migration strategies and different optimizers and learning rates, and comparison experiments with the five classic network structures of ResNet50, YOLOV3, MobileNetV2, VGG16, and YOLOV4 are also tested. The test data show that the recognition accuracy rates of qualified images and the three types of defective images (Qualified Assembly, Missing Current Plate, Wrong Number of Stacks, and Reverse Stack) can reach 99.64%, 98.17%, 99.11%, and 95.40%, respectively, the overall recognition accuracy rate can reach 98.10%. The test results illustrate the model can detect thermal battery defects more accurately and quickly, and has good defect diagnosis ability, which is nearly 5% higher than the traditional method, and a new solution for defect detection in practical industrial scenarios of thermal battery is provided.

Aiming at the lack of large public single molten salt battery data sets, to reduce the labour-consuming, to improve the insufficient learning ability of traditional diagnostic methods in the production of single molten salt battery, an image recognition model for molten salt battery defects based on transfer learning is proposed. First, some pre-processing operations and image enhancement on the single molten salt battery image are performed. Second, the backbone of recognition model is built based on VGG16 network, and the selective kernel (SK) convolution module is adopted after the bottleneck layer, convolution kernel with an appropriate size can be selected adaptively through input feature map; Third, the FC is taken the place of a GAP layer, a dropout layer, and other fine-tuning operations are added, a simplified model called V-VGGNet is got; Finally, the weight parameters obtained from the pre-training on the ImageNet data set are transferred to the single molten salt battery image recognition model V-VGGNet. For different network structures and different training strategies, comparative experiments of performance tests are conducted. The test data manifest that the accuracy rates of V-VGGNet network for three categories of defective images (Missing Negative Electrode, Broken Tab, and Missing Current Collector) and Assembly Normal images can reach 95.14%, 98.79%, 98.21%, and 99.41%, the average accuracy can achieve 97.91%, good performance improvement of the single molten salt battery is improved, it is about 3% higher compared to other well-knows networks, which verified the feasibility of V-VGGNet model and the effectiveness of the improvement.

Alzheimer’s disease (AD) is a prevalent neurodegenerative disease in aging populations. Complex network analysis helps quantify brain features for AD diagnosis, yet existing studies use coarse brain atlases and fixed thresholds, failing to capture subtle topological changes along disease progression. This study used the fine-grained Zalesky_1024 atlas to optimize thresholds and characterize topological alterations across AD progression. Resting-state functional magnetic resonance imaging (fMRI) data from cognitively normal (CN), early mild cognitive impairment (EMCI), late mild cognitive impairment (LMCI) and AD groups were used to construct brain networks. Topological characteristics were then analyzed across thresholds to track progressive changes from CN→EMCI→LMCI→AD. Finally, support vector machine (SVM) was applied to explore the classification performance of topological characteristics. Results showed threshold-dependent topological alterations along the progression. SVM with betweenness centrality and degree achieved superior classification for EMCI versus AD and CN versus AD. Furthermore, the Zalesky_1024 template outperformed the traditional automated anatomical labeling 90 (AAL_90) template in terms of sensitivity, specificity, accuracy, and area under the curve for classification. These results reveal progressive brain topological degradation across the AD spectrum and supply imaging topological markers to advance AD staging and neuroimaging diagnostic tools.